SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.08261 · ICLR · 2025

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

U Berkeley, Zhen Dong, Shuicheng Yan, Xiangtai Li, Lei Zhu, Tian Ye, Wei Chow, Enxin Song, Jinbin Bai, Enc Vq, Comp, Decomp

arXiv · PDF · Open in the Atlas

Code that ran

4 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 8 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.08261.json · badge: /api/ran/2410.08261.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
viiika/Meissonic canonical (classifier label)
classifier basis: classifier_2025
4 ran · 8 no recorded run
FunctionStatusWhere it lives
FluxPosEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("d7869221fbf85eed")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, FluxPosEmbed: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
import torch.nn as nn
from typing import List

torch.manual_seed(0)

# FluxPosEmbed constructor takes theta (int) and axes_dim (List[int])
# Looking at the forward method:
# - ids is expected to be a tensor with shape [..., n_axes]
# - ids.squeeze().float().cpu().numpy() converts it to numpy
# - For each axis i, pos[:, i] is indexed, so pos must be 2D
# - axes_dim[i] is used as dim parameter for get_1d_rotary_pos_embed
# - n_axes = ids.shape[-1] must match len(axes_dim)

theta = 10000
axes_dim = [8, 6]  # Two different dimensions for two axes

ARGS = {
    "theta": theta,
    "axes_dim": axes_dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FluxPosEmbed — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FluxPosEmbed output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_1d_rotary_pos_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("5267e615858f198f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (4, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    "dim": 4,
    "pos": np.array([0, 1, 2, 3]),
    "theta": 10000.0,
    "use_real": False,
    "linear_factor": 1.0,
    "ntk_factor": 1.0,
    "repeat_interleave_real": True,
    "freqs_dtype": torch.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 2) — shape (4, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_2d_rotary_pos_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("648219193abb0da5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Define ARGS dict with all parameters for get_2d_rotary_pos_embed
ARGS = {
    "embed_dim": 8,
    "crops_coords": ((0, 0), (4, 3)),
    "grid_size": (2, 3),
    "use_real": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_3d_rotary_pos_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("7baace01d2459d49")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Define arguments for get_3d_rotary_pos_embed
ARGS = {
    "embed_dim": 16,
    "crops_coords": ((0, 0), (4, 5)),
    "grid_size": (3, 4),
    "temporal_size": 2,
    "theta": 10000,
    "use_real": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ConvMlmLayer Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("b5bd4bc3ff1420f4")
How it ran

no invocation recorded.

FusedFluxAttnProcessor2_0 Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("76e74eb4929058d0")
How it ran

no invocation recorded.

Simple_UVitBlock Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("65d68c48e8af4c9e")
How it ran

no invocation recorded.

SingleTransformerBlock Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("f738ac02f57b6614")
How it ran

no invocation recorded.

Transformer2DModel Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("a11765e9087a4203")
How it ran

no invocation recorded.

TransformerBlock Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("8d6351d29b4f55c6")
How it ran

no invocation recorded.

UVit2DConvEmbed Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("2c3b0dc5adf5f251")
How it ran

no invocation recorded.

get_2d_rotary_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
viiika/Meissonic/src/transformer.py
code served (permissive licence) · get_code("837ad33d0af915e3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 6 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 6 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
ConvMlmLayer
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2505.23606 (2025-05)
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
Simple_UVitBlock
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2505.23606 (2025-05)
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
SingleTransformerBlock
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2505.23606 (2025-05)
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
TransformerBlock
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2505.23606 (2025-05)
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
UVit2DConvEmbed
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2505.23606 (2025-05)
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
get_1d_rotary_pos_embed
brick of this paper's assembly: helper
1 other paper
1 later
2505.23606 (2025-05)
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations, advanced positional encoding strategies, and optimized sampling conditions, Meissonic substantially improves MIM's performance and efficiency. Additionally, we leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing models like SDXL in generating highquality, high-resolution images. Extensive experiments validate Meissonic's capabilities, demonstrating its potential as a new standard in text-to-image synthesis. We release a model checkpoint capable of producing 1024 × 1024 resolution images.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.08261")
get_code_for_paper("2410.08261")
have("2410.08261")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.08261.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.08261.svg)](https://syntology.ai/paper/2410.08261)

Connect an agent — have() is free.